{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:AKNZIVKZBQ47IJON3HPGUUDRRI","short_pith_number":"pith:AKNZIVKZ","canonical_record":{"source":{"id":"2406.05756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T12:23:14Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"title_canon_sha256":"d6cfc5b463c5c90ecb2fca7b0ce749937588209809385bd5eaf99a1b76a4d9cf","abstract_canon_sha256":"4bef13d34461e41bafa9d58b7daa82c3f1d77d979349e83024daf7a231a9b0d0"},"schema_version":"1.0"},"canonical_sha256":"029b9455590c39f425cdd9de6a50718a1424c69d1bd637aeee4f87cde3f27a2c","source":{"kind":"arxiv","id":"2406.05756","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05756","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05756v1","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05756","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"AKNZIVKZBQ47","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"AKNZIVKZBQ47IJON","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"AKNZIVKZ","created_at":"2026-07-05T08:29:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:AKNZIVKZBQ47IJON3HPGUUDRRI","target":"record","payload":{"canonical_record":{"source":{"id":"2406.05756","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T12:23:14Z","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"title_canon_sha256":"d6cfc5b463c5c90ecb2fca7b0ce749937588209809385bd5eaf99a1b76a4d9cf","abstract_canon_sha256":"4bef13d34461e41bafa9d58b7daa82c3f1d77d979349e83024daf7a231a9b0d0"},"schema_version":"1.0"},"canonical_sha256":"029b9455590c39f425cdd9de6a50718a1424c69d1bd637aeee4f87cde3f27a2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:29:33.271030Z","signature_b64":"WkwZ7ehkZzv50tcoq6YTlAY+Z7BX4/1s/6oX0b0cCpD6HYN0Lm8tCNmkNQWtLzA2DSCK8DNTpw9+LhIwlAvvDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"029b9455590c39f425cdd9de6a50718a1424c69d1bd637aeee4f87cde3f27a2c","last_reissued_at":"2026-07-05T08:29:33.270686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:29:33.270686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.05756","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:29:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pYCvF330IX6D5icVSLXptRbfsymGDuMUz8zHa79N/ud67bbTf7Era3eueqm2/XsKRvJ0r513LkQau6B3260PDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:38:19.074226Z"},"content_sha256":"37bb565927d8c9ebec4e920c7620589d4764c8bb2c1d2bcbc307e1bd03786608","schema_version":"1.0","event_id":"sha256:37bb565927d8c9ebec4e920c7620589d4764c8bb2c1d2bcbc307e1bd03786608"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:AKNZIVKZBQ47IJON3HPGUUDRRI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV","cs.MM"],"primary_cat":"cs.AI","authors_text":"Binhao Wu, Mengfei Du, Xuanjing Huang, Zejun Li, Zhongyu Wei","submitted_at":"2024-06-09T12:23:14Z","abstract_excerpt":"The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly evaluated, leaving the gap between current LVLMs and qualified embodied intelligence unknown. Therefore, we construct EmbSpatial-Bench, a benchmark for evaluating embodied spatial understanding of LVLMs.The benchmark is automatically derived from embodied scenes and covers 6 spatial relationships from an egocentric perspective.Experiments expose the insufficient capacity of cur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05756","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2406.05756/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:29:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bOQj91/vaSpmcGNak0JjrCmPhU/3z3a4j8QCeTiFXhQeshSstQSw986L6JbUsX9riJwTU5wBcBB8xGG3ISllBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:38:19.077565Z"},"content_sha256":"62a62add19c723c9833cc243e9ef404da1ab5a431835797f653c792bb0fb464b","schema_version":"1.0","event_id":"sha256:62a62add19c723c9833cc243e9ef404da1ab5a431835797f653c792bb0fb464b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AKNZIVKZBQ47IJON3HPGUUDRRI/bundle.json","state_url":"https://pith.science/pith/AKNZIVKZBQ47IJON3HPGUUDRRI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AKNZIVKZBQ47IJON3HPGUUDRRI/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T07:38:19Z","links":{"resolver":"https://pith.science/pith/AKNZIVKZBQ47IJON3HPGUUDRRI","bundle":"https://pith.science/pith/AKNZIVKZBQ47IJON3HPGUUDRRI/bundle.json","state":"https://pith.science/pith/AKNZIVKZBQ47IJON3HPGUUDRRI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AKNZIVKZBQ47IJON3HPGUUDRRI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:AKNZIVKZBQ47IJON3HPGUUDRRI","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4bef13d34461e41bafa9d58b7daa82c3f1d77d979349e83024daf7a231a9b0d0","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T12:23:14Z","title_canon_sha256":"d6cfc5b463c5c90ecb2fca7b0ce749937588209809385bd5eaf99a1b76a4d9cf"},"schema_version":"1.0","source":{"id":"2406.05756","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.05756","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"arxiv_version","alias_value":"2406.05756v1","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.05756","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_12","alias_value":"AKNZIVKZBQ47","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_16","alias_value":"AKNZIVKZBQ47IJON","created_at":"2026-07-05T08:29:33Z"},{"alias_kind":"pith_short_8","alias_value":"AKNZIVKZ","created_at":"2026-07-05T08:29:33Z"}],"graph_snapshots":[{"event_id":"sha256:62a62add19c723c9833cc243e9ef404da1ab5a431835797f653c792bb0fb464b","target":"graph","created_at":"2026-07-05T08:29:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2406.05756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent rapid development of Large Vision-Language Models (LVLMs) has indicated their potential for embodied tasks.However, the critical skill of spatial understanding in embodied environments has not been thoroughly evaluated, leaving the gap between current LVLMs and qualified embodied intelligence unknown. Therefore, we construct EmbSpatial-Bench, a benchmark for evaluating embodied spatial understanding of LVLMs.The benchmark is automatically derived from embodied scenes and covers 6 spatial relationships from an egocentric perspective.Experiments expose the insufficient capacity of cur","authors_text":"Binhao Wu, Mengfei Du, Xuanjing Huang, Zejun Li, Zhongyu Wei","cross_cats":["cs.CL","cs.CV","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T12:23:14Z","title":"EmbSpatial-Bench: Benchmarking Spatial Understanding for Embodied Tasks with Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.05756","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:37bb565927d8c9ebec4e920c7620589d4764c8bb2c1d2bcbc307e1bd03786608","target":"record","created_at":"2026-07-05T08:29:33Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4bef13d34461e41bafa9d58b7daa82c3f1d77d979349e83024daf7a231a9b0d0","cross_cats_sorted":["cs.CL","cs.CV","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-06-09T12:23:14Z","title_canon_sha256":"d6cfc5b463c5c90ecb2fca7b0ce749937588209809385bd5eaf99a1b76a4d9cf"},"schema_version":"1.0","source":{"id":"2406.05756","kind":"arxiv","version":1}},"canonical_sha256":"029b9455590c39f425cdd9de6a50718a1424c69d1bd637aeee4f87cde3f27a2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"029b9455590c39f425cdd9de6a50718a1424c69d1bd637aeee4f87cde3f27a2c","first_computed_at":"2026-07-05T08:29:33.270686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:29:33.270686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WkwZ7ehkZzv50tcoq6YTlAY+Z7BX4/1s/6oX0b0cCpD6HYN0Lm8tCNmkNQWtLzA2DSCK8DNTpw9+LhIwlAvvDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:29:33.271030Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.05756","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:37bb565927d8c9ebec4e920c7620589d4764c8bb2c1d2bcbc307e1bd03786608","sha256:62a62add19c723c9833cc243e9ef404da1ab5a431835797f653c792bb0fb464b"],"state_sha256":"27468198e1c7954a799b8fd64afaea243a58f6c5e82242e35a5daeedafdb9173"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xUNpzC2KVn/2a6SQsRmcs321+E+e3LHBmj24vDTPlDt6BvTDaNXkKjUOUkftjyxGFY5bdaZTt1DEXvGEKOrCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:38:19.156750Z","bundle_sha256":"89949cf7f36110a918e58aa302f07b953b445aac4d208cecc420a96b5190a5d0"}}